© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35033
    Prev
    Next
    INDEX
    Explanations

    action verbs with pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zij
    -0.11
     senin
    -0.10
    548
    -0.09
    æĤ¨çļĦ
    -0.09
    iser
    -0.09
    divid
    -0.09
    ovny
    -0.09
    èĩªå·±çļĦ
    -0.09
    irs
    -0.08
     sizin
    -0.08
    POSITIVE LOGITS
     him
    0.31
     us
    0.29
     them
    0.25
     me
    0.22
     you
    0.17
     onları
    0.16
     ihn
    0.16
     sizi
    0.14
    him
    0.14
     onu
    0.13
    Activations Density 0.104%

    No Known Activations